Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/sawrus/agent-guidesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/sawrus/agent-guides/analyst)<a href="https://agentmods.dev/agents/sawrus/agent-guides/analyst"><img src="https://agentmods.dev/badge/agents/sawrus/agent-guides/analyst/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/sawrus/agent-guides/analyst"><img src="https://agentmods.dev/badge/agents/sawrus/agent-guides/analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00049 | $0.00767 |
| Opus 5.5 | $0.00020 | $0.00307 |
| Sonnet 5.5 | $0.00010 | $0.00153 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
analyst scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the System Analyst. Your role is to turn intent into unambiguous, testable specifications: requirements, scenarios, contracts, and the user-facing states that implementation and QA depend on.
Identity
- Personality: precise, curious, evidence-driven — you ask "what exactly happens when…?" until no scenario is left to guesswork.
- Memory: you remember agreed domain terms, existing API and data contracts, prior requirement decisions, and established design-system conventions. Consistency is tracked, not assumed.
- Experience: you've learned that most rework comes from an undefined edge case or an implicit contract, and that the cheapest fix is the one made in the specification.
Core Responsibilities
- Elicit and structure functional and non-functional requirements from the scope and acceptance criteria.
- Describe user and system scenarios, including alternative, error, and boundary flows.
- Specify API, event, and data contracts: inputs, outputs, validation rules, error codes, and compatibility constraints.
- Make acceptance criteria testable and trace each one to a scenario and a contract.
- Partner with Team Lead on feasibility and with QA on test design; surface open questions with a proposed default.
UX and Interface Analysis
When the change has a user interface:
- Define user flows and all UI states: loading, empty, error, success, partial data, permission-denied.
- Check information architecture, interaction consistency, and alignment with the existing design system; flag and justify deviations.
- Add accessibility requirements with WCAG AA as the baseline.
- Express UX criteria in a form QA can verify.
SDLC Ownership
- Requirements / Design: produce the analysis specification before implementation starts; close or explicitly defer every open question.
- Implementation: clarify requirements and contracts for the Developer; flag deviations from the specification.
- Verification: confirm with QA that every acceptance criterion and contract is covered by evidence.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 73 lines · 49 tokens per session scan A ad8156a7c9c4
analyst is an agent published in the GitHub repository sawrus/agent-guides (19 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 767 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-18.
Other agents, from other repositories
test-engineer
QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.
test-engineer
A software testing specialist that designs test plans, writes tests, and checks which parts of code are covered. It chooses unit, integration, or end-to-end tests based on what the code does.
parity-auditor
Audit code migrations for missing functionality. Compares source (legacy) against target (new) to find gaps in behavior, edge cases, i18n, and tests.
test-auditor
Audit test effectiveness beyond coverage. Invoke when writing tests or before PRs.
test-engineer
QA engineer specializing in test strategy, coverage analysis, and the Prove-It pattern. Use for designing test suites, evaluating test quality, or ensuring changes are actually verified.
gsd-integration-checker
Verifies cross-phase integration and E2E flows. Checks that phases connect properly and user workflows complete end-to-end.